1 TADPOLE and RPART

RPART Analysis

1.1 Loading the libraries

library("FRESA.CAD")
library(readxl)
library(igraph)
pander::panderOptions('digits', 3)
pander::panderOptions('table.split.table', 400)
pander::panderOptions('keep.trailing.zeros',TRUE)

1.2 Loading BSWiMS Results

opo <- par(no.readonly = TRUE)

load("~/GitHub/BSWiMS/TADPOLE_BSWIMS_Results.RData")
op <- opo

2 Predicting ADAS13

Here we will diagnose ADAS13

2.1 Learning ADAS13

RPARTml <- rpart::rpart(ADAS13~.,TADPOLECrossMRITrain)
pander::pander(as.matrix(RPARTml$variable.importance))
M_ST24TA 17843.5
M_ST24CV 11509.9
Hippocampus 11035.4
M_ST29SV 10790.9
M_ST12SV 8803.0
M_ST60TA 5845.0
M_ST40CV 2701.8
M_ST52TA 2126.4
M_ST13TA 1852.5
M_ST31TA 1804.7
M_ST32TA 1503.1
M_ST13SA 1476.9
M_ST52CV 1252.5
M_ST57TA 1193.3
M_ST24SA 1078.3
WholeBrain 1012.5
M_ST59TA 1002.0
M_ST32CV 990.3
M_ST31SA 967.2
RD_ST31CV 908.1
RD_ST57TA 813.0
RD_ST24TA 740.9
M_ST60CV 733.1
M_ST45CV 686.9
M_ST40TA 683.1
M_ST30SV 677.7
M_ST56TA 632.9
M_ST31CV 613.1
M_ST46CV 542.1
M_ST129TA 488.1
M_ST52TS 486.3
M_ST14TS 484.3
M_ST16SV 484.3
RD_ST35TA 484.3
RD_ST39TS 484.3
M_ST15TA 459.6
M_ST49CV 447.4
RD_ST36TS 423.8
M_ST129CV 414.4
M_ST129SA 414.4
M_ST48SA 414.4
RD_ST47SA 414.4
RD_ST49CV 414.4
M_ST31TS 405.2
M_ST36TS 405.2
M_ST13CV 369.2
M_ST40SA 369.2
M_ST26TA 356.9
M_ST48TA 340.0
M_ST45SA 317.0
M_ST34TA 312.2
M_ST58TA 299.4
M_ST60SA 287.6
M_ST51TA 287.2
M_ST15CV 281.8
M_ST45TA 281.8
M_ST39CV 263.9
M_ST62CV 256.2
M_ST55TA 237.3
RD_ST62TA 213.0
M_ST57CV 191.3
M_ST36TA 169.5
M_ST32SA 165.7
M_ST35TA 143.5
M_ST26SA 142.0
M_ST59SA 142.0
RD_ST24TS 123.5
M_ST43TS 82.3
M_ST56TS 82.3
RD_ST56TA 82.3 

prreg <- predictionStats_regression(cbind(TADPOLECrossMRITest$ADAS13,predict(RPARTml,TADPOLECrossMRITest)),"ADAS13")

ADAS13 

pander::pander(prreg)

  • corci:

    cor    
    0.615 0.567 0.659

  • biasci: -0.419, -0.990 and 0.153

  • RMSEci: 7.74, 7.35 and 8.16

  • spearmanci:

    50% 2.5% 97.5%
    0.578 0.522 0.63

  • MAEci:

    50% 2.5% 97.5%
    6.01 5.66 6.37

  • pearson:

    Pearson’s product-moment correlation: predictions[, 1] and predictions[, 2]
    Test statistic df P value Alternative hypothesis cor
    20.7 702 1.49e-74 * * * two.sided 0.615 
par(op)
par(mar = rep(0.2, 4))
plot(RPARTml,branch = 0.2,uniform = TRUE, compress = TRUE,margin = 0.1)
text(RPARTml,use.n = TRUE,all=TRUE,cex=0.5)

par(op)

2.2 Decorrelated

RPARTmlD <- rpart::rpart(ADAS13~.,TADPOLECrossMRITrainD)
pander::pander(as.matrix(RPARTmlD$variable.importance))
Ba_Hippocampus 19147
Ba_M_ST37SV 5569
Ba_M_ST65SV 5188
Ba_M_ST59TA 4516
De_M_ST58TA 3969
De_M_ST11SV 3791
Ba_RD_ST40CV 2932
De_M_ST47TA 2226
De_Ventricles 2156
De_M_ST24TA 2136
De_M_ST29SV 1241
RD_ST29SV 1184
De_M_ST38SA 1135
RD_ST32TA 1055
De_M_ST34TA 995
RD_ST40TA 957
De_RD_ST40SA 899
De_M_ST12SV 812
De_M_ST31TA 785
Ba_RD_ST26CV 717
De_M_ST15TS 665
Ba_M_ST35SA 663
Ba_RD_ST48SA 621
De_RD_ST31CV 530
Ba_RD_ST50SA 484
M_ST13TS 474
Ba_M_ST56SA 474
Ba_M_ST45TS 454
Ba_RD_ST49CV 454
M_ST38CV 454
RD_ST52TA 454
RD_ST12SV 451
RD_ST47TA 432
M_ST24TS 395
De_M_ST60TA 388
RD_ST129CV 388
De_M_ST55SA 379
De_M_ST62TA 379
M_ST35CV 379
De_ST6SV 378
M_ST38TS 374
De_M_ST45TA 346
De_M_ST55TA 346
M_ST47TS 346
Ba_M_ST32SA 338
M_ST60TS 337
De_M_ST36TA 326
Ba_ST68SV 322
RD_ST30SV 311
Ba_RD_ST26SA 307
De_M_ST62CV 307
Ba_ICV 298
De_M_ST38TA 279
De_M_ST13TA 274
De_RD_ST45CV 273
De_M_ST40SA 267
Ba_M_ST129TS 239
Ba_M_ST34SA 239
De_M_ST44TA 233
De_M_ST54TA 233
Ba_RD_ST39CV 226
RD_ST58TA 218
De_M_ST15TA 214
M_ST43TS 214
RD_ST54TA 212
De_M_ST24CV 194
De_M_ST40CV 194
De_M_ST56TA 194
De_ST2SV 187
M_ST46TS 184
De_M_ST25TA 151
RD_ST13TA 146
RD_ST26TA 146
De_M_ST30SV 141
RD_ST13TS 141
De_M_ST129TA 125
De_M_ST52TA 125
De_ST1SV 125
De_M_ST56TS 109
M_ST52TS 109
M_ST57TS 109 

prreg <- predictionStats_regression(cbind(TADPOLECrossMRITestD$ADAS13,predict(RPARTmlD,TADPOLECrossMRITestD)),"ADAS13")

ADAS13 

pander::pander(prreg)

  • corci:

    cor    
    0.536 0.481 0.587

  • biasci: -0.5991, -1.2189 and 0.0206

  • RMSEci: 8.40, 7.98 and 8.86

  • spearmanci:

    50% 2.5% 97.5%
    0.565 0.507 0.614

  • MAEci:

    50% 2.5% 97.5%
    6.33 5.94 6.74

  • pearson:

    Pearson’s product-moment correlation: predictions[, 1] and predictions[, 2]
    Test statistic df P value Alternative hypothesis cor
    16.8 702 1.4e-53 * * * two.sided 0.536 
par(op)
par(mar = rep(0.2, 4))
plot(RPARTmlD,branch = 0.2,uniform = TRUE, compress = TRUE,margin = 0.1)
text(RPARTmlD,use.n = TRUE,all=TRUE,cex=0.75)

par(op)

3 Diagnosis MCI vs AD

3.1 Learning

TADPOLE_DX_TRAIN$DX <- as.factor(TADPOLE_DX_TRAIN$DX)

RPARTDXml <- rpart::rpart(DX~.,TADPOLE_DX_TRAIN)
#RPARTDXml <- rpart::rpart(DX~.,TADPOLE_DX_TRAIN,
#                          control = rpart::rpart.control(xval = 10, minbucket = 2, cp = 0.01))
#RPARTDXml <- rpart::prune(RPARTDXml, cp = 0.02)

pander::pander(as.matrix(RPARTDXml$variable.importance))
M_ST24TA 37.887
M_ST12SV 26.613
M_ST24CV 25.070
M_ST29SV 20.055
Hippocampus 19.678
M_ST60TA 15.080
M_ST26SA 8.557
M_ST32SA 7.137
RD_ST46SA 7.101
RD_ST52TA 7.009
M_ST32CV 6.727
M_ST16SV 6.196
M_ST52TA 6.080
M_ST57TA 5.932
M_ST57SA 5.825
RD_ST15SA 5.352
RD_ST38CV 5.248
M_ST54CV 5.108
RD_ST66SV 4.964
ST127SV 4.423
WholeBrain 4.095
M_ST15SA 3.893
M_ST31CV 3.893
M_ST40SA 3.893
M_ST13TA 3.658
RD_ST15CV 3.568
M_ST26CV 3.427
M_ST52SA 3.295
M_ST31TA 3.224
M_ST36TA 3.160
M_ST56TA 3.160
M_ST54SA 3.131
M_ST32TA 3.090
M_ST39CV 2.801
M_ST45TS 2.708
M_ST56CV 2.708
RD_ST52TS 2.708
M_ST129TA 2.528
M_ST50TA 2.528
M_ST15TS 2.379
M_ST43CV 2.379
RD_ST43CV 2.379
RD_ST43SA 2.379
M_ST39SA 2.307
M_ST56SA 2.187
M_ST60SA 2.142
M_ST49SA 1.978
RD_ST38SA 1.874
RD_ST31CV 1.869
ST4SV 1.822
M_ST38SA 1.758
M_ST48SA 1.758
M_ST129SA 1.483
M_ST25TA 1.402
ST5SV 1.097
RD_ST31SA 1.014
RD_ST13CV 0.937
ST1SV 0.878
ST3SV 0.878
RD_ST26CV 0.750
RD_ST26TA 0.750
M_ST13SA 0.676
M_ST52TS 0.676
M_ST58TS 0.676
M_ST59TS 0.676 

prBin <- predictionStats_binary(cbind(TADPOLE_DX_TEST$DX,predict(RPARTDXml,TADPOLE_DX_TEST)[,2]),"MCI vs Dementia")

MCI vs Dementia 

pander::pander(prBin$aucs)
est lower upper
0.699 0.644 0.754 
pander::pander(prBin$accc)
est lower upper
0.702 0.654 0.748 
pander::pander(prBin$berror)
50% 2.5% 97.5%
0.408 0.354 0.461 
pander::pander(prBin$sensitivity)
est lower upper
0.367 0.272 0.471 
par(op)
par(mar = rep(0.2, 4))
plot(RPARTDXml,branch = 0.2,uniform = TRUE, compress = TRUE,margin = 0.1)
text(RPARTDXml,use.n = TRUE,all=TRUE,cex=0.75)

par(op)

3.1.1 Decorrelated ML

TADPOLE_DX_TRAIND$DX <- as.factor(TADPOLE_DX_TRAIND$DX)

RPARTDXmlD <- rpart::rpart(DX~.,TADPOLE_DX_TRAIND)
pander::pander(as.matrix(RPARTDXmlD$variable.importance))
Ba_M_ST24TA 37.887
De_M_ST30SV 16.282
De_M_ST29SV 10.933
De_M_ST26SA 8.557
Ba_RD_ST57SA 7.836
De_ST5SV 7.642
RD_ST52TA 7.377
De_M_ST11SV 7.351
Ba_RD_ST46SA 7.101
De_M_ST26TA 6.597
M_ST53SV 6.439
RD_ST34TA 6.329
M_ST61SV 5.945
RD_ST15TS 5.867
M_ST26TS 5.334
Ba_RD_ST15SA 5.225
RD_ST60TS 4.697
De_M_ST45TA 4.423
M_ST17SV 4.325
De_ST127SV 3.855
De_M_ST52TS 3.531
De_M_ST45CV 3.135
RD_ST14TS 3.135
Ba_M_ST18SV 3.127
De_M_ST26CV 2.939
De_M_ST39TA 2.786
RD_ST129TA 2.786
RD_ST57TA 2.786
Ba_M_ST43TS 2.773
Ba_M_ST45TS 2.773
RD_ST55TA 2.528
De_M_ST57CV 2.516
RD_ST11SV 2.516
Ba_Ventricles 2.013
De_RD_ST34CV 1.989
De_Hippocampus 1.959
De_WholeBrain 1.959
Ba_RD_ST55SA 1.956
De_RD_ST48CV 1.956
M_ST13TS 1.956
RD_ST50TA 1.956
RD_ST24TS 1.914
M_ST54TS 1.896
M_ST21SV 1.740
De_M_ST52TA 1.566
RD_ST13TS 1.566
De_M_ST36TA 1.524
De_M_ST47TA 1.524
De_M_ST50TA 1.524
De_M_ST55TA 1.524
M_ST36TS 1.524
De_RD_ST15CV 1.372
AGE 1.304
De_M_ST37SV 1.266
De_M_ST59CV 1.266
De_M_ST31SA 1.229
RD_ST24TA 1.229
RD_ST52TS 1.229
Ba_M_ST52SA 1.097
RD_ST43TA 1.085
Ba_RD_ST31SA 1.014
De_ST10CV 1.014
De_ST2SV 0.980
RD_ST35TS 0.980
De_M_ST13TA 0.904
De_M_ST15TS 0.878
De_M_ST39TS 0.878
Ba_M_ST65SV 0.815
De_M_ST57TA 0.784
ST9SV 0.784
Ba_M_ST13SA 0.676
De_M_ST23CV 0.676
Ba_M_ST31TA 0.615
De_M_ST14TA 0.615
Ba_M_ST57SA 0.407 


prBin <- predictionStats_binary(cbind(TADPOLE_DX_TESTD$DX,predict(RPARTDXmlD,TADPOLE_DX_TESTD)[,2]),"MCI vs Dementia")

MCI vs Dementia 

pander::pander(prBin$aucs)
est lower upper
0.685 0.623 0.748 
pander::pander(prBin$accc)
est lower upper
0.728 0.681 0.772 
pander::pander(prBin$berror)
50% 2.5% 97.5%
0.38 0.329 0.434 
pander::pander(prBin$sensitivity)
est lower upper
0.398 0.3 0.502 
par(op)
par(mar = rep(0.2, 4))
plot(RPARTDXmlD,branch = 0.2,uniform = TRUE, compress = TRUE,margin = 0.1)
text(RPARTDXmlD,use.n = TRUE,all=TRUE,cex=0.75)

par(op)

4 Diagnosis NL vs AD

4.1 Learning

TADPOLE_DX_NLDE_TRAIN$DX <- as.factor(TADPOLE_DX_NLDE_TRAIN$DX)

RPARTDXmlNLDE <- rpart::rpart(DX~.,TADPOLE_DX_NLDE_TRAIN)
pander::pander(as.matrix(RPARTDXmlNLDE$variable.importance))
M_ST24TA 94.64
Hippocampus 63.53
M_ST29SV 62.69
M_ST24CV 61.98
M_ST32TA 49.87
M_ST12SV 49.42
M_ST32CV 16.50
M_ST13TA 6.24
M_ST30SV 4.71
RD_ST52TA 4.19
M_ST40CV 4.12
M_ST32SA 3.61
M_ST34CV 3.14
M_ST13CV 3.09
M_ST44CV 1.80
RD_ST26CV 1.80
M_ST26SA 1.20
ST3SV 1.20 

#RPARTDXmlNLDE <- rpart::rpart(DX~.,TADPOLE_DX_NLDE_TRAIN,
#                          control = rpart::rpart.control(xval = 10, minbucket = 2, cp = 0.0))
#RPARTDXmlNLDE <- rpart::prune(RPARTDXmlNLDE, cp = 0.02)

prBin <- predictionStats_binary(cbind(TADPOLE_DX_NLDE_TEST$DX,predict(RPARTDXmlNLDE,TADPOLE_DX_NLDE_TEST)[,2]),"NL vs Dementia")

NL vs Dementia 

pander::pander(prBin$aucs)
est lower upper
0.838 0.789 0.887 
pander::pander(prBin$accc)
est lower upper
0.835 0.786 0.877 
pander::pander(prBin$berror)
50% 2.5% 97.5%
0.205 0.154 0.254 
pander::pander(prBin$sensitivity)
est lower upper
0.663 0.561 0.756 
par(op)
par(mar = rep(0.2, 4))
plot(RPARTDXmlNLDE,branch = 0.2,uniform = TRUE, compress = TRUE,margin = 0.1)
text(RPARTDXmlNLDE,use.n = TRUE,all=TRUE,cex=0.75)

par(op)

4.2 Decorrelated Set

4.2.1 Learning

TADPOLE_DX_NLDE_TRAIND$DX <- as.factor(TADPOLE_DX_NLDE_TRAIND$DX)

RPARTDXmlNLDED <- rpart::rpart(DX~.,TADPOLE_DX_NLDE_TRAIND)
pander::pander(as.matrix(RPARTDXmlNLDED$variable.importance))
Ba_M_ST24TA 100.513
De_M_ST29SV 32.665
Ba_M_ST31TA 27.420
De_M_ST44TA 25.127
De_M_ST30SV 22.614
De_M_ST36TA 22.614
De_M_ST51TA 17.582
M_ST13TS 6.054
De_Hippocampus 4.947
De_M_ST59CV 4.402
De_M_ST43TA 3.822
Ba_M_ST13SA 3.668
De_M_ST57CV 3.668
RD_ST13TA 3.668
RD_ST59TA 3.668
De_M_ST49TA 3.058
AGE 2.293
De_M_ST58TA 2.293
Ba_M_ST26TS 2.018
De_M_ST26TA 2.018
De_M_ST15TA 1.345
De_M_ST54TA 1.345
M_ST129TS 1.345
De_M_ST13TA 1.237
De_M_ST32TA 1.237
De_ST3SV 0.618
RD_ST50TA 0.618 

#                          control = rpart::rpart.control(xval = 10, minbucket = 2, cp = 0.01))
#RPARTDXmlNLDED <- rpart::prune(RPARTDXmlNLDED, cp = 0.02)

prBin <- predictionStats_binary(cbind(TADPOLE_DX_NLDE_TESTD$DX,predict(RPARTDXmlNLDED,TADPOLE_DX_NLDE_TESTD)[,2]),"NL vs Dementia")

NL vs Dementia 

pander::pander(prBin$aucs)
est lower upper
0.848 0.8 0.895 
pander::pander(prBin$accc)
est lower upper
0.842 0.794 0.883 
pander::pander(prBin$berror)
50% 2.5% 97.5%
0.18 0.131 0.229 
pander::pander(prBin$sensitivity)
est lower upper
0.745 0.647 0.828 
par(op)
par(mar = rep(0.2, 4))
plot(RPARTDXmlNLDED,branch = 0.2,uniform = TRUE, compress = TRUE,margin = 0.1)
text(RPARTDXmlNLDED,use.n = TRUE,all=TRUE,cex=0.75)

par(op)

5 Prognosis MCI to AD Conversion

5.1 Learning Survival


bConvml <- rpart::rpart(Surv(TimeToEvent,status)~.,TADPOLE_Conv_TRAIN)
pander::pander(as.matrix(bConvml$variable.importance))
ADAS13 92.05
FAQ 75.30
ADAS11 75.06
Hippocampus 57.90
RAVLT_perc_forgetting 43.90
RAVLT_immediate 42.96
M_ST24TA 42.74
RD_ST13TA 29.83
M_ST12SV 29.82
WholeBrain 29.22
M_ST40CV 28.54
M_ST29SV 21.52
M_ST58TA 18.90
M_ST31CV 18.02
M_ST35TA 14.44
RD_ST55TA 13.23
RD_ST12SV 12.30
M_ST51SA 11.53
M_ST13CV 11.32
RD_ST16SV 10.27
M_ST45SA 10.23
M_ST26CV 9.27
M_ST40SA 9.27
RD_ST58TA 8.97
M_ST58CV 8.92
ICV 8.75
ST10CV 8.75
M_ST43TA 8.48
RD_ST14SA 8.43
M_ST52CV 8.29
M_ST26TA 8.24
M_ST32TA 8.24
M_ST44TS 8.20
M_ST59TA 8.01
M_ST36CV 7.72
M_ST13TA 7.44
M_ST14CV 7.23
RD_ST47CV 6.94
RD_ST55CV 6.94
M_ST16SV 6.71
M_ST56SA 6.49
M_ST11SV 6.02
RD_ST57TS 6.02
ST128SV 5.95
ST68SV 5.95
M_ST25TA 5.29
M_ST48SA 5.29
Gender 5.22
M_ST34TA 5.22
M_ST45CV 5.11
M_ST24CV 4.54
M_ST49SA 4.32
RD_ST51TA 4.32
M_ST46TS 4.29
M_ST32SA 3.90
M_ST46SA 3.90
M_ST57TS 3.90
RD_ST31SA 3.78
M_ST47SA 2.94
M_ST60SA 2.94
RD_ST39CV 2.94
ST2SV 2.94
ST6SV 2.94
M_ST51TA 2.83
M_ST52TA 2.83
M_ST56TA 2.83
RD_ST60SA 2.56
M_ST52SA 1.92 

ptestr <- predict(bConvml,TADPOLE_Conv_TEST)
ptestl <- log(ptestr)
boxplot(ptestl~TADPOLE_Conv_TEST$status)

boxplot(ptestr~TADPOLE_Conv_TEST$status)


par(op)
par(mar = rep(0.2, 4))
plot(bConvml,branch = 0.2,uniform = TRUE, compress = TRUE,margin = 0.1)
text(bConvml,use.n = TRUE,all=TRUE,cex=0.75)

par(op)


perdsurv <- cbind(TADPOLE_Conv_TEST$TimeToEvent,
                  TADPOLE_Conv_TEST$status,
                  ptestl,
                  ptestr)

if (max(ptestl)>0 && min(ptestl)<0 )
{
  prSurv <- predictionStats_survival(perdsurv,"MCI to  AD Conversion")
  pander::pander(prSurv$CIRisk)
  pander::pander(prSurv$CILp)
  pander::pander(prSurv$spearmanCI)
}

5.2

50% 2.5% 97.5%
0.269 0.0864 0.452 

prBin <- predictionStats_binary(cbind(TADPOLE_Conv_TEST$status,ptestl),"MCI to  AD Conversion")

MCI to AD Conversion 



par(op)
pander::pander(prBin$aucs)
est lower upper
0.736 0.675 0.797 
pander::pander(prBin$CM.analysis$tab)
  Outcome + Outcome - Total
Test + 66 60 126
Test - 32 115 147
Total 98 175 273

The decorrelation

5.3 Decorrelated

5.3.1 Learning



bConvmlD <- rpart::rpart(Surv(TimeToEvent,status)~.,TADPOLE_Conv_TRAIND)
pander::pander(as.matrix(bConvmlD$variable.importance))
FAQ 102.56
Ba_ADAS13 96.64
De_Hippocampus 61.31
Ba_M_ST59TA 34.80
Ba_RAVLT_learning 33.05
MMSE 24.55
De_Ventricles 22.18
De_RAVLT_perc_forgetting 20.16
RD_ST13TA 19.49
Ba_ST68SV 14.21
RD_ST30SV 13.36
RD_ST129TA 13.30
Ba_M_ST36SA 13.24
Ba_M_ST59SA 11.77
De_M_ST14TA 11.52
De_RD_ST62CV 11.39
De_M_ST47TS 11.07
RD_ST56TA 10.47
De_M_ST36TA 9.64
De_M_ST56TA 9.27
M_ST46CV 9.06
Ba_RD_ST14SA 8.43
Ba_M_ST13SA 7.49
De_M_ST56CV 7.23
RD_ST12SV 7.23
De_M_ST60SA 7.06
De_RD_ST50CV 7.06
RD_ST36TA 7.06
RD_ST50TA 7.06
De_M_ST31SA 6.68
Ba_M_ST129SA 6.62
De_M_ST50TA 6.28
RD_ST62TA 6.21
Ba_M_ST32SA 6.15
RD_ST38TA 6.15
De_M_ST51TA 6.02
RD_ST57TS 6.02
Ba_M_ST26SA 5.67
Ba_AGE 5.57
M_ST44TS 5.57
Ba_RD_ST34SA 5.47
RD_ST31TS 5.24
RD_ST36TS 5.24
De_M_ST40TA 5.18
M_ST38TS 5.18
Ba_M_ST37SV 5.08
Ba_M_ST14TS 4.91
De_RD_ST13CV 4.59
De_WholeBrain 4.45
Ba_M_ST57SA 4.20
De_RAVLT_immediate 4.20
De_M_ST129CV 4.20
De_M_ST15CV 4.20
De_M_ST32CV 4.20
RD_ST25TS 4.20
De_M_ST60TA 3.21
M_ST62TS 3.21
RD_ST31TA 3.06
De_M_ST35TA 2.67
M_ST46TS 2.67
Ba_M_ST15SA 2.52
De_M_ST39SA 2.52
M_ST44SA 2.52
RD_ST44SA 2.27
RD_ST45TS 2.21
De_ADAS11 2.14
Ba_ICV 2.03
Ba_M_ST35TS 2.03
De_M_ST31TS 2.03
De_M_ST47TA 2.03
ST9SV 2.03
De_M_ST15TA 1.76
De_M_ST49TA 1.76
De_M_ST62TA 1.76
De_ST4SV 1.76
Ba_M_ST14SA 1.70
De_M_ST40TS 1.70 

ptestr <- predict(bConvmlD,TADPOLE_Conv_TESTD)
ptestl <- log(ptestr)
boxplot(ptestl~TADPOLE_Conv_TEST$status)

boxplot(ptestr~TADPOLE_Conv_TEST$status)


perdsurv <- cbind(TADPOLE_Conv_TEST$TimeToEvent,
                  TADPOLE_Conv_TEST$status,
                  ptestl,
                  ptestr)


if (max(ptestl)>0 && min(ptestl)<0 )
{
  prSurv <- predictionStats_survival(perdsurv,"MCI to  AD Conversion")
  pander::pander(prSurv$CIRisk)
  pander::pander(prSurv$CILp)
  pander::pander(prSurv$spearmanCI)
}

5.4

50% 2.5% 97.5%
0.257 0.0579 0.437 

prBin <- predictionStats_binary(cbind(TADPOLE_Conv_TESTD$status,ptestl),"MCI to  AD Conversion")

MCI to AD Conversion 

pander::pander(prBin$aucs)
est lower upper
0.711 0.648 0.774 
pander::pander(prBin$CM.analysis$tab)
  Outcome + Outcome - Total
Test + 82 77 159
Test - 16 98 114
Total 98 175 273 

par(op)
par(mar = rep(0.2, 4))
plot(bConvmlD,branch = 0.2,uniform = TRUE, compress = TRUE,margin = 0.1)
text(bConvmlD,use.n = TRUE,all=TRUE,cex=0.75)

par(op)

5.4.1 The End

.